Computer Vision: How Bots See The World Around Them

In my piece on neural network art, I looked at how bots generate images based on their existing โ€˜knowledgeโ€™ of shape and form. These computers are trained on large data sets of images, all classified and tagged so the machine can make sense of them. Googleโ€™s Deep Dream, for example, uses a set of ImageNet material with 120 dog categories, explaining why almost everything it hallucinates has some kind of dog, however subtle.

Projects like Deep Dream are more of an artistic side-project than a useful tool, but the tech itโ€™s based on is a bridge towards computer programs being able to make sense of the world around them โ€” whether thatโ€™s an image tagger for a search engine, or a robot with nuanced spacial awareness.…   [continue reading]